{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T13:22:44Z","timestamp":1783171364653,"version":"3.54.6"},"reference-count":63,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100021160","name":"Chinese Academy of Sciences Shanghai Institute of Microsystem and Information Technology","doi-asserted-by":"publisher","award":["6142804230104"],"award-info":[{"award-number":["6142804230104"]}],"id":[{"id":"10.13039\/501100021160","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Computer Vision and Image Understanding"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.cviu.2026.104828","type":"journal-article","created":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T16:22:32Z","timestamp":1780676552000},"page":"104828","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["OCC-MLLM-V1: Occlusion reasoning with commonsense-guided Multi-modal LLM based agent via internal Chain-of-Thoughts (CoTs)"],"prefix":"10.1016","volume":"270","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0164-1953","authenticated-orcid":false,"given":"Chaoyi","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingdong","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Pei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lijie","family":"Xia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianpo","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baoqing","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8855-8628","authenticated-orcid":false,"given":"Xinhan","family":"Di","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.cviu.2026.104828_b1","series-title":"2024 5th International Conference on Advancements in Computational Sciences","first-page":"1","article-title":"Dynamic adoptive gaussian mixture model for multi-object detection over natural scenes","author":"Ahmed","year":"2024"},{"key":"10.1016\/j.cviu.2026.104828_b2","series-title":"Llava-onevision-1.5: Fully open framework for democratized multimodal training","author":"An","year":"2025"},{"key":"10.1016\/j.cviu.2026.104828_b3","series-title":"\u03c00: A vision-language-action flow model for general robot control","author":"Black","year":"2024"},{"key":"10.1016\/j.cviu.2026.104828_b4","series-title":"Proceedings of the European Conference on Computer Vision","first-page":"361","article-title":"Contactpose: A dataset of grasps with object contact and hand pose","author":"Brahmbhatt","year":"2020"},{"key":"10.1016\/j.cviu.2026.104828_b5","doi-asserted-by":"crossref","unstructured":"Cao, Z., Radosavovic, I., Kanazawa, A., Malik, J., 2021. Reconstructing hand-object interactions in the wild. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. ICCV, pp. 12417\u201312426.","DOI":"10.1109\/ICCV48922.2021.01219"},{"key":"10.1016\/j.cviu.2026.104828_b6","series-title":"Multimodal structured generation: Cvpr\u2019s 2nd mmfm challenge technical report","author":"Cesista","year":"2024"},{"key":"10.1016\/j.cviu.2026.104828_b7","doi-asserted-by":"crossref","unstructured":"Chao, Y.-W., Yang, W., Xiang, Y., Molchanov, P., Handa, A., Tremblay, J., Narang, Y., Wyk, K., Iqbal, U., Birchfield, S., et al., 2021. Dexycb: A benchmark for capturing hand grasping of objects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 9044\u20139053.","DOI":"10.1109\/CVPR46437.2021.00893"},{"key":"10.1016\/j.cviu.2026.104828_b8","doi-asserted-by":"crossref","unstructured":"Chen, Z., Chen, S., Schmid, C., Laptev, I., 2023. Gsdf: Geometry-driven signed distance functions for 3d hand-object reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 12890\u201312900.","DOI":"10.1109\/CVPR52729.2023.01239"},{"key":"10.1016\/j.cviu.2026.104828_b9","doi-asserted-by":"crossref","first-page":"4008","DOI":"10.1109\/TIP.2021.3068645","article-title":"Joint hand-object 3d reconstruction from a single image with cross-branch feature fusion","volume":"30","author":"Chen","year":"2021","journal-title":"IEEE Trans. Image Process. (TIP)"},{"key":"10.1016\/j.cviu.2026.104828_b10","series-title":"Wang, expanding performance boundaries of open-source multimodal models with model, data,and test-time scaling","author":"Chen","year":"2025"},{"issue":"12","key":"10.1016\/j.cviu.2026.104828_b11","doi-asserted-by":"crossref","DOI":"10.1007\/s11432-024-4231-5","article-title":"How far are we to gpt-4v? closing the gap to commercial multimodal models with open-source suites","volume":"67","author":"Chen","year":"2024","journal-title":"Sci. China Inf. Sci."},{"key":"10.1016\/j.cviu.2026.104828_b12","doi-asserted-by":"crossref","unstructured":"Chen, Z., Wu, J., Wang, W., Su, W., Chen, G., Xing, S., Zhong, M., Zhang, Q., Zhu, X., Lu, L., et al., 2024a. Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 24185\u201324198.","DOI":"10.1109\/CVPR52733.2024.02283"},{"key":"10.1016\/j.cviu.2026.104828_b13","series-title":"Claude 3.7","author":"Claude","year":"2025"},{"issue":"12","key":"10.1016\/j.cviu.2026.104828_b14","doi-asserted-by":"crossref","first-page":"2250","DOI":"10.3390\/electronics13122250","article-title":"An advanced approach to object detection and tracking in robotics and autonomous vehicles using yolov8 and lidar data fusion","volume":"13","author":"Dai","year":"2024","journal-title":"Electronics"},{"key":"10.1016\/j.cviu.2026.104828_b15","series-title":"Deepseek-r1: incentivizing reasoning capability in llms via reinforcement learning","author":"DeepSeek-AI","year":"2025"},{"key":"10.1016\/j.cviu.2026.104828_b16","series-title":"Benchmarks and challenges in pose estimation for egocentric hand interactions with objects","author":"Fan","year":"2024"},{"key":"10.1016\/j.cviu.2026.104828_b17","doi-asserted-by":"crossref","DOI":"10.3389\/fnbot.2025.1585386","article-title":"Focus: Object-centric world models for robotic manipulation","volume":"19","author":"Ferraro","year":"2025","journal-title":"Front. Neurorobotics"},{"key":"10.1016\/j.cviu.2026.104828_b18","series-title":"2025 National Conference on Communications","first-page":"1","article-title":"Occrobnet: Occlusion robust network for accurate 3d interacting hand-object pose estimation","author":"Garg","year":"2025"},{"key":"10.1016\/j.cviu.2026.104828_b19","series-title":"Gemini 2.5: pushing the frontier with advanced reasoning, multimodality, long context and next generation agentic capabilities","author":"Google","year":"2025"},{"key":"10.1016\/j.cviu.2026.104828_b20","doi-asserted-by":"crossref","unstructured":"Hampali, S., Rad, M., Oberweger, M., Lepetit, V., 2020. Honnotate: A method for 3d annotation of hand and object poses. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 3196\u20133206.","DOI":"10.1109\/CVPR42600.2020.00326"},{"key":"10.1016\/j.cviu.2026.104828_b21","doi-asserted-by":"crossref","unstructured":"Hasson, Y., Varol, G., Tzionas, D., Kalevatykh, I., Black, M., Laptev, I., Schmid, C., 2019. Learning joint reconstruction of hands and manipulated objects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 11807\u201311816.","DOI":"10.1109\/CVPR.2019.01208"},{"issue":"12","key":"10.1016\/j.cviu.2026.104828_b22","doi-asserted-by":"crossref","first-page":"3760","DOI":"10.3390\/s24123760","article-title":"Static and dynamic hand gestures: a review of techniques of virtual reality manipulation","volume":"24","author":"Herbert","year":"2024","journal-title":"Sensors"},{"key":"10.1016\/j.cviu.2026.104828_b23","series-title":"Binary classifier optimization for large language model alignment","author":"Jung","year":"2024"},{"key":"10.1016\/j.cviu.2026.104828_b24","doi-asserted-by":"crossref","first-page":"162467","DOI":"10.1109\/ACCESS.2025.3609980","article-title":"Vision-language-action models for robotics: A review towards real-world applications","volume":"13","author":"Kawaharazuka","year":"2025","journal-title":"IEEE Access"},{"key":"10.1016\/j.cviu.2026.104828_b25","series-title":"Openvla: An open-source vision-language-action model","author":"Kim","year":"2024"},{"issue":"3","key":"10.1016\/j.cviu.2026.104828_b26","doi-asserted-by":"crossref","first-page":"736","DOI":"10.1007\/s11263-020-01401-3","article-title":"Compositional convolutional neural networks: A robust and interpretable model for object recognition under occlusion","volume":"129","author":"Kortylewski","year":"2021","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.cviu.2026.104828_b27","series-title":"Training language models to self-correct via reinforcement learning","author":"Kumar","year":"2024"},{"key":"10.1016\/j.cviu.2026.104828_b28","series-title":"European Conference on Computer Vision","first-page":"740","article-title":"Microsoft coco: Common objects in context","author":"Lin","year":"2014"},{"key":"10.1016\/j.cviu.2026.104828_b29","author":"Liu","year":"2024"},{"key":"10.1016\/j.cviu.2026.104828_b30","series-title":"A survey on vision-language-action models for embodied ai","author":"Ma","year":"2024"},{"key":"10.1016\/j.cviu.2026.104828_b31","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2022.109217","article-title":"3D hand pose estimation from a single rgb image by weighting the occlusion and classification","volume":"136","author":"Mahdikhanlou","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.cviu.2026.104828_b32","series-title":"Cosmos-reason1: from physical common sense to embodied reasoning","author":"NVIDIA","year":"2025"},{"key":"10.1016\/j.cviu.2026.104828_b33","series-title":"Chatgpt","author":"OpenAI","year":"2023"},{"key":"10.1016\/j.cviu.2026.104828_b34","series-title":"Gpt-4o system card","author":"OpenAI","year":"2024"},{"issue":"12","key":"10.1016\/j.cviu.2026.104828_b35","doi-asserted-by":"crossref","first-page":"2883","DOI":"10.1109\/TPAMI.2017.2759736","article-title":"Hand-object contact force estimation from markerless visual tracking","volume":"40","author":"Pham","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell. (TPAMI)"},{"key":"10.1016\/j.cviu.2026.104828_b36","series-title":"2024 5th International Conference on Mobile Computing and Sustainable Informatics","first-page":"218","article-title":"Improved occlusion handling in object recognition by enhancing image quality and suitable illumination techniques","author":"Priya","year":"2024"},{"key":"10.1016\/j.cviu.2026.104828_b37","series-title":"Prism: A framework for decoupling and assessing the capabilities of vlms","author":"Qiao","year":"2024"},{"key":"10.1016\/j.cviu.2026.104828_b38","series-title":"Occ-mllm: Empowering multimodal large language model for the understanding of occluded objects","author":"Qiu","year":"2024"},{"key":"10.1016\/j.cviu.2026.104828_b39","series-title":"Direct preference optimization: Your language model is secretly a reward model","author":"Rafailov","year":"2024"},{"key":"10.1016\/j.cviu.2026.104828_b40","series-title":"Ai agents vs. agentic ai: a conceptual taxonomy, applications and challenges","author":"Sapkota","year":"2025"},{"key":"10.1016\/j.cviu.2026.104828_b41","first-page":"25278","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","volume":"Vol. 35","author":"Schuhmann","year":"2022"},{"key":"10.1016\/j.cviu.2026.104828_b42","doi-asserted-by":"crossref","unstructured":"Shao, S., Li, Z., Zhang, T., Peng, C., Yu, G., Zhang, X., Li, J., Sun, J., 2019. Objects365: A large-scale, high-quality dataset for object detection. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. ICCV, pp. 8430\u20138439.","DOI":"10.1109\/ICCV.2019.00852"},{"key":"10.1016\/j.cviu.2026.104828_b43","series-title":"Scene exploration by vision-language models","author":"Sripada","year":"2025"},{"key":"10.1016\/j.cviu.2026.104828_b44","doi-asserted-by":"crossref","first-page":"172","DOI":"10.1007\/s11263-016-0895-4","article-title":"Capturing hands in action using discriminative salient points and physics simulation","volume":"118","author":"Tzionas","year":"2016","journal-title":"Int. J. Comput. Vis. (IJCV)"},{"key":"10.1016\/j.cviu.2026.104828_b45","series-title":"Enhancing the reasoning ability of multimodal large language models via mixed preference optimization","author":"Wang","year":"2024"},{"key":"10.1016\/j.cviu.2026.104828_b46","author":"Wang","year":"2024"},{"key":"10.1016\/j.cviu.2026.104828_b47","series-title":"Occ-mllm-cot-alpha: Towards multi-stage occlusion recognition based on large language models via 3d-aware supervision and chain-of-thoughts guidance","author":"Wang","year":"2025"},{"key":"10.1016\/j.cviu.2026.104828_b48","first-page":"24824","article-title":"Chain-of-thought prompting elicits reasoning in large language models","volume":"Vol. 35","author":"Wei","year":"2022"},{"key":"10.1016\/j.cviu.2026.104828_b49","series-title":"Grok-3","author":"xAI","year":"2025"},{"key":"10.1016\/j.cviu.2026.104828_b50","series-title":"Llava-cot: Let vision language models reason step-by-step","author":"Xu","year":"2025"},{"key":"10.1016\/j.cviu.2026.104828_b51","doi-asserted-by":"crossref","unstructured":"Xu, H., Wang, T., Tang, X., Fu, C.-W., 2023. H2onet: Hand-occlusion-and-orientation-aware network for real-time 3d hand mesh reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 17048\u201317058.","DOI":"10.1109\/CVPR52729.2023.01635"},{"key":"10.1016\/j.cviu.2026.104828_b52","series-title":"Embodiedbench: Comprehensive benchmarking multi-modal large language models for vision-driven embodied agents","author":"Yang","year":"2025"},{"key":"10.1016\/j.cviu.2026.104828_b53","series-title":"Occ-mllm-alpha: Empowering multi-modal large language model for the understanding of occluded objects with self-supervised test-time learning","author":"Yang","year":"2024"},{"key":"10.1016\/j.cviu.2026.104828_b54","doi-asserted-by":"crossref","first-page":"11809","DOI":"10.52202\/075280-0517","article-title":"Tree of thoughts: Deliberate problem solving with large language models","volume":"36","author":"Yao","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.cviu.2026.104828_b55","doi-asserted-by":"crossref","unstructured":"Ye, Y., Gupta, A., Tulsiani, S., 2022. What\u2019s in your hands? 3d reconstruction of generic objects in hands. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 3895\u20133905.","DOI":"10.1109\/CVPR52688.2022.00387"},{"key":"10.1016\/j.cviu.2026.104828_b56","doi-asserted-by":"crossref","unstructured":"Zellers, R., Bisk, Y., Farhadi, A., Choi, Y., 2019. From recognition to cognition: Visual commonsense reasoning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. CVPR, pp. 6720\u20136731.","DOI":"10.1109\/CVPR.2019.00688"},{"key":"10.1016\/j.cviu.2026.104828_b57","series-title":"Moho: Learning single-view hand-held object reconstruction with multi-view occlusion-aware supervision","author":"Zhang","year":"2024"},{"key":"10.1016\/j.cviu.2026.104828_b58","series-title":"Llavar: Enhanced visual instruction tuning for text-rich image understanding","author":"Zhang","year":"2023"},{"issue":"4","key":"10.1016\/j.cviu.2026.104828_b59","doi-asserted-by":"crossref","first-page":"588","DOI":"10.1007\/s11633-025-1542-8","article-title":"A survey of embodied learning for object-centric robotic manipulation","volume":"22","author":"Zheng","year":"2025","journal-title":"Mach. Intell. Res."},{"key":"10.1016\/j.cviu.2026.104828_b60","series-title":"Jarvis: A neuro-symbolic commonsense reasoning framework for conversational embodied agents","author":"Zheng","year":"2025"},{"key":"10.1016\/j.cviu.2026.104828_b61","series-title":"Minigpt-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"10.1016\/j.cviu.2026.104828_b62","series-title":"Robustness of object recognition under extreme occlusion in humans and computational models","author":"Zhu","year":"2019"},{"key":"10.1016\/j.cviu.2026.104828_b63","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Tian, Y., Metaxas, D., Doll\u00e1r, P., 2017. Semantic amodal segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 1464\u20131472.","DOI":"10.1109\/CVPR.2017.320"}],"container-title":["Computer Vision and Image Understanding"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314226001955?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1077314226001955?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T13:05:25Z","timestamp":1783170325000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1077314226001955"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":63,"alternative-id":["S1077314226001955"],"URL":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104828","relation":{"is-supplemented-by":[{"id-type":"uri","id":"https:\/\/github.com\/chaoyiwang09\/occ-mllm","asserted-by":"subject"}]},"ISSN":["1077-3142"],"issn-type":[{"value":"1077-3142","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"OCC-MLLM-V1: Occlusion reasoning with commonsense-guided Multi-modal LLM based agent via internal Chain-of-Thoughts (CoTs)","name":"articletitle","label":"Article Title"},{"value":"Computer Vision and Image Understanding","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.cviu.2026.104828","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104828"}}